AI RESEARCH
DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
arXiv CS.LG
•
ArXi:2604.07166v1 Announce Type: cross Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work proposes DINO-QPM, which converts these powerful but entangled features into contrastive, class-independent representations that are interpretable by humans.